Skip to Main content Skip to Navigation
Conference papers

Object Detection Using Strongly-Supervised Deformable Part Models

Hossein Azizpour 1 Ivan Laptev 2 
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Deformable part-based models [1, 2] achieve state-of-the-art performance for object detection, but rely on heuristic initialization during training due to the optimization of non-convex cost function. This paper investigates limitations of such an initialization and extends earlier methods using additional supervision. We explore strong supervision in terms of annotated object parts and use it to (i) improve model initialization, (ii) optimize model structure, and (iii) handle partial occlusions. Our method is able to deal with sub-optimal and incomplete annotations of object parts and is shown to benefit from semi-supervised learning setups where part-level annotation is provided for a fraction of positive examples only. Experimental results are reported for the detection of six animal classes in PASCAL VOC 2007 and 2010 datasets. We demonstrate significant improvements in detection performance compared to the LSVM [1] and the Poselet [3] object detectors.
Document type :
Conference papers
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Suha Kwak Connect in order to contact the contributor
Submitted on : Thursday, September 11, 2014 - 6:16:24 PM
Last modification on : Thursday, March 17, 2022 - 10:08:39 AM
Long-term archiving on: : Friday, December 12, 2014 - 10:58:06 AM


Files produced by the author(s)




Hossein Azizpour, Ivan Laptev. Object Detection Using Strongly-Supervised Deformable Part Models. ECCV 2012 - European Conference on Computer Vision, Oct 2012, Florence, Italy. pp.836-849, ⟨10.1007/978-3-642-33718-5_60⟩. ⟨hal-01063338⟩



Record views


Files downloads